While attention mechanisms have been proven to be effective in many NLP
...
Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sa...
During the past few decades, missing-data problems have been studied
ext...
Index structures are important for efficient data access, which have bee...
In some applications, an experimental unit is composed of two distinct b...
The testing problem for the order of finite mixture models has a long hi...
In this paper, we focus on policy discrepancy in return-based deep Q-net...
We establish a general framework for statistical inferences with
non-pro...
The asymptotic behaviour of the commonly used bootstrap percentile confi...